Multi-label Classification Based on Label-Aware Variational Autoencoder
With the rise of the Internet, all kinds of data are growing rapidly, and how to utilize these sample data efficiently has become an important issue in the field of data mining. The multi-label classification task, as an important task in the field of machine learning and data mining, aims to label...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2025-03-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2405061.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850235944874016768 |
|---|---|
| author | SUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian |
| author_facet | SUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian |
| author_sort | SUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian |
| collection | DOAJ |
| description | With the rise of the Internet, all kinds of data are growing rapidly, and how to utilize these sample data efficiently has become an important issue in the field of data mining. The multi-label classification task, as an important task in the field of machine learning and data mining, aims to label samples with multiple label categories. Most of the current methods only learn embedding representations for feature branches, do not take into account the semantic relevance between features and labels, and lack effective constraints on the feature embedding space, which leads to insufficient relevance of the learnt feature embeddings. Meanwhile, in terms of label relevance learning, most of the existing methods mainly focus on low-order label relevance, and thus the problem of insufficient learning of high-order relevance between multiple labels becomes more prominent when facing complex actual labeling scenarios. Therefore, in order to solve the above problems, this paper proposes a multi-label classification method based on label-aware variational self-encoder from embedding representation learning and label relevance learning. Specifically, for embedding representation learning, this paper proposes to use feature and label dual-stream variational self-encoders to simultaneously learn and align the embedding space of features and labels, and add label guidance to the feature embedding space to enhance feature embedding. Meanwhile, a label semantic-based cross-attention mechanism is used to add specific label information to the feature embedding, and finally discriminative feature embeddings after label sensing are obtained. For label relevance learning, the multi-layer self-attention mechanism in the shared decoder is used to fully fuse the similarity information of multiple labels, and through the co-occurring interactions between different labels, the label higher-order relevance representations are learnt and used for cross-aware feature embedding. Experimental results obtained on datasets from four different domains show that the proposed method can effectively enhance feature and label embedding and fully capture the higher-order correlation information between labels for multi-label classification tasks, and the significant superiority of the proposed method in performance is verified through a comparative analysis with state-of-the-art algorithms in terms of multiple evaluation metrics. |
| format | Article |
| id | doaj-art-5de1355a93fc43cbb95f4d619715ff56 |
| institution | OA Journals |
| issn | 1673-9418 |
| language | zho |
| publishDate | 2025-03-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj-art-5de1355a93fc43cbb95f4d619715ff562025-08-20T02:02:06ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182025-03-0119371472310.3778/j.issn.1673-9418.2405061Multi-label Classification Based on Label-Aware Variational AutoencoderSUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian01. School of Computer Science and Technology, Beijing Jiaotong University, Beijing 100044, China 2. Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, ChinaWith the rise of the Internet, all kinds of data are growing rapidly, and how to utilize these sample data efficiently has become an important issue in the field of data mining. The multi-label classification task, as an important task in the field of machine learning and data mining, aims to label samples with multiple label categories. Most of the current methods only learn embedding representations for feature branches, do not take into account the semantic relevance between features and labels, and lack effective constraints on the feature embedding space, which leads to insufficient relevance of the learnt feature embeddings. Meanwhile, in terms of label relevance learning, most of the existing methods mainly focus on low-order label relevance, and thus the problem of insufficient learning of high-order relevance between multiple labels becomes more prominent when facing complex actual labeling scenarios. Therefore, in order to solve the above problems, this paper proposes a multi-label classification method based on label-aware variational self-encoder from embedding representation learning and label relevance learning. Specifically, for embedding representation learning, this paper proposes to use feature and label dual-stream variational self-encoders to simultaneously learn and align the embedding space of features and labels, and add label guidance to the feature embedding space to enhance feature embedding. Meanwhile, a label semantic-based cross-attention mechanism is used to add specific label information to the feature embedding, and finally discriminative feature embeddings after label sensing are obtained. For label relevance learning, the multi-layer self-attention mechanism in the shared decoder is used to fully fuse the similarity information of multiple labels, and through the co-occurring interactions between different labels, the label higher-order relevance representations are learnt and used for cross-aware feature embedding. Experimental results obtained on datasets from four different domains show that the proposed method can effectively enhance feature and label embedding and fully capture the higher-order correlation information between labels for multi-label classification tasks, and the significant superiority of the proposed method in performance is verified through a comparative analysis with state-of-the-art algorithms in terms of multiple evaluation metrics.http://fcst.ceaj.org/fileup/1673-9418/PDF/2405061.pdfmulti-label classification; embedded space learning; variational autoencoder; transformer; label correlation |
| spellingShingle | SUN Hongjian, XU Pengyu, LIU Bing, JING Liping, YU Jian Multi-label Classification Based on Label-Aware Variational Autoencoder Jisuanji kexue yu tansuo multi-label classification; embedded space learning; variational autoencoder; transformer; label correlation |
| title | Multi-label Classification Based on Label-Aware Variational Autoencoder |
| title_full | Multi-label Classification Based on Label-Aware Variational Autoencoder |
| title_fullStr | Multi-label Classification Based on Label-Aware Variational Autoencoder |
| title_full_unstemmed | Multi-label Classification Based on Label-Aware Variational Autoencoder |
| title_short | Multi-label Classification Based on Label-Aware Variational Autoencoder |
| title_sort | multi label classification based on label aware variational autoencoder |
| topic | multi-label classification; embedded space learning; variational autoencoder; transformer; label correlation |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2405061.pdf |
| work_keys_str_mv | AT sunhongjianxupengyuliubingjinglipingyujian multilabelclassificationbasedonlabelawarevariationalautoencoder |